Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Features:

   - Add "uretprobes" - an optimization to uprobes, like kretprobes are
     an optimization to kprobes.  "perf probe -x file sym%return" now
     works like kretprobes.  By Oleg Nesterov.

   - Introduce per core aggregation in 'perf stat', from Stephane
     Eranian.

   - Add memory profiling via PEBS, from Stephane Eranian.

   - Event group view for 'annotate' in --stdio, --tui and --gtk, from
     Namhyung Kim.

   - Add support for AMD NB and L2I "uncore" counters, by Jacob Shin.

   - Add Ivy Bridge-EP uncore support, by Zheng Yan

   - IBM zEnterprise EC12 oprofile support patchlet from Robert Richter.

   - Add perf test entries for checking breakpoint overflow signal
     handler issues, from Jiri Olsa.

   - Add perf test entry for for checking number of EXIT events, from
     Namhyung Kim.

   - Add perf test entries for checking --cpu in record and stat, from
     Jiri Olsa.

   - Introduce perf stat --repeat forever, from Frederik Deweerdt.

   - Add --no-demangle to report/top, from Namhyung Kim.

   - PowerPC fixes plus a couple of cleanups/optimizations in uprobes
     and trace_uprobes, by Oleg Nesterov.

  Various fixes and refactorings:

   - Fix dependency of the python binding wrt libtraceevent, from
     Naohiro Aota.

   - Simplify some perf_evlist methods and to allow 'stat' to share code
     with 'record' and 'trace', by Arnaldo Carvalho de Melo.

   - Remove dead code in related to libtraceevent integration, from
     Namhyung Kim.

   - Revert "perf sched: Handle PERF_RECORD_EXIT events" to get 'perf
     sched lat' back working, by Arnaldo Carvalho de Melo

   - We don't use Newt anymore, just plain libslang, by Arnaldo Carvalho
     de Melo.

   - Kill a bunch of die() calls, from Namhyung Kim.

   - Fix build on non-glibc systems due to libio.h absence, from Cody P
     Schafer.

   - Remove some perf_session and tracing dead code, from David Ahern.

   - Honor parallel jobs, fix from Borislav Petkov

   - Introduce tools/lib/lk library, initially just removing duplication
     among tools/perf and tools/vm.  from Borislav Petkov

  ... and many more I missed to list, see the shortlog and git log for
  more details."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (136 commits)
  perf/x86/intel/P4: Robistify P4 PMU types
  perf/x86/amd: Fix AMD NB and L2I "uncore" support
  perf/x86/amd: Remove old-style NB counter support from perf_event_amd.c
  perf/x86: Check all MSRs before passing hw check
  perf/x86/amd: Add support for AMD NB and L2I "uncore" counters
  perf/x86/intel: Add Ivy Bridge-EP uncore support
  perf/x86/intel: Fix SNB-EP CBO and PCU uncore PMU filter management
  perf/x86: Avoid kfree() in CPU_{STARTING,DYING}
  uprobes/perf: Avoid perf_trace_buf_prepare/submit if ->perf_events is empty
  uprobes/tracing: Don't pass addr=ip to perf_trace_buf_submit()
  uprobes/tracing: Change create_trace_uprobe() to support uretprobes
  uprobes/tracing: Make seq_printf() code uretprobe-friendly
  uprobes/tracing: Make register_uprobe_event() paths uretprobe-friendly
  uprobes/tracing: Make uprobe_{trace,perf}_print() uretprobe-friendly
  uprobes/tracing: Introduce is_ret_probe() and uretprobe_dispatcher()
  uprobes/tracing: Introduce uprobe_{trace,perf}_print() helpers
  uprobes/tracing: Generalize struct uprobe_trace_entry_head
  uprobes/tracing: Kill the pointless local_save_flags/preempt_count calls
  uprobes/tracing: Kill the pointless seq_print_ip_sym() call
  uprobes/tracing: Kill the pointless task_pt_regs() calls
  ...

4 files changed, 22 insertions, 22 deletions

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 10b8f23fab0f..92669cd182a6 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -351,4 +351,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
  */
 #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
 
+/* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */
+#ifdef CONFIG_KPROBES
+# define __kprobes      __attribute__((__section__(".kprobes.text")))
+#else
+# define __kprobes
+#endif
 #endif /* __LINUX_COMPILER_H */
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 4b6ef4d33cc2..ca1d27a0d6a6 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -29,6 +29,7 @@
  *              <jkenisto@us.ibm.com>  and Prasanna S Panchamukhi
  *              <prasanna@in.ibm.com> added function-return probes.
  */
+#include <linux/compiler.h>     /* for __kprobes */
 #include <linux/linkage.h>
 #include <linux/list.h>
 #include <linux/notifier.h>
@@ -49,16 +50,11 @@
 #define KPROBE_REENTER          0x00000004
 #define KPROBE_HIT_SSDONE       0x00000008
 
-/* Attach to insert probes on any functions which should be ignored*/
-#define __kprobes       __attribute__((__section__(".kprobes.text")))
-
 #else /* CONFIG_KPROBES */
 typedef int kprobe_opcode_t;
 struct arch_specific_insn {
         int dummy;
 };
-#define __kprobes
-
 #endif /* CONFIG_KPROBES */
 
 struct kprobe;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1d795df6f4cf..e0373d26c244 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -21,7 +21,6 @@
  */
 
 #ifdef CONFIG_PERF_EVENTS
-# include <linux/cgroup.h>
 # include <asm/perf_event.h>
 # include <asm/local64.h>
 #endif
@@ -128,6 +127,7 @@ struct hw_perf_event {
                         int             event_base_rdpmc;
                         int             idx;
                         int             last_cpu;
+                        int             flags;
 
                         struct hw_perf_event_extra extra_reg;
                         struct hw_perf_event_extra branch_reg;
@@ -299,22 +299,7 @@ struct swevent_hlist {
 #define PERF_ATTACH_GROUP       0x02
 #define PERF_ATTACH_TASK        0x04
 
-#ifdef CONFIG_CGROUP_PERF
-/*
- * perf_cgroup_info keeps track of time_enabled for a cgroup.
- * This is a per-cpu dynamically allocated data structure.
- */
-struct perf_cgroup_info {
-        u64                             time;
-        u64                             timestamp;
-};
-
-struct perf_cgroup {
-        struct                          cgroup_subsys_state css;
-        struct                          perf_cgroup_info *info; /* timing info, one per cpu */
-};
-#endif
-
+struct perf_cgroup;
 struct ring_buffer;
 
 /**
@@ -583,11 +568,13 @@ struct perf_sample_data {
                 u32     reserved;
         }                               cpu_entry;
         u64                             period;
+        union  perf_mem_data_src        data_src;
         struct perf_callchain_entry     *callchain;
         struct perf_raw_record          *raw;
         struct perf_branch_stack        *br_stack;
         struct perf_regs_user           regs_user;
         u64                             stack_user_size;
+        u64                             weight;
 };
 
 static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -601,6 +588,8 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
         data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
         data->regs_user.regs = NULL;
         data->stack_user_size = 0;
+        data->weight = 0;
+        data->data_src.val = 0;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
@@ -831,6 +820,7 @@ do {									\
 struct perf_pmu_events_attr {
         struct device_attribute attr;
         u64 id;
+        const char *event_str;
 };
 
 #define PMU_EVENT_ATTR(_name, _var, _id, _show)                         \
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 02b83db8e2c5..06f28beed7c2 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -38,6 +38,8 @@ struct inode;
 #define UPROBE_HANDLER_REMOVE           1
 #define UPROBE_HANDLER_MASK             1
 
+#define MAX_URETPROBE_DEPTH             64
+
 enum uprobe_filter_ctx {
         UPROBE_FILTER_REGISTER,
         UPROBE_FILTER_UNREGISTER,
@@ -46,6 +48,9 @@ enum uprobe_filter_ctx {
 
 struct uprobe_consumer {
         int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs);
+        int (*ret_handler)(struct uprobe_consumer *self,
+                                unsigned long func,
+                                struct pt_regs *regs);
         bool (*filter)(struct uprobe_consumer *self,
                                 enum uprobe_filter_ctx ctx,
                                 struct mm_struct *mm);
@@ -68,6 +73,8 @@ struct uprobe_task {
         enum uprobe_task_state          state;
         struct arch_uprobe_task         autask;
 
+        struct return_instance          *return_instances;
+        unsigned int                    depth;
         struct uprobe                   *active_uprobe;
 
         unsigned long                   xol_vaddr;
@@ -100,6 +107,7 @@ struct uprobes_state {
 extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
+extern bool __weak is_trap_insn(uprobe_opcode_t *insn);
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
 extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);